© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11092
    Prev
    Next
    INDEX
    Explanations

    syscall imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.45
    a
    -0.44
    i
    -0.42
    y
    -0.38
    o
    -0.37
    à¸Ļ
    -0.36
    er
    -0.36
    en
    -0.34
    åľ¨
    -0.33
    es
    -0.32
    POSITIVE LOGITS
    tempts
    0.29
    	TokenName
    0.26
    imately
    0.26
    odore
    0.25
    lectual
    0.25
    etheless
    0.24
    itionally
    0.23
    _ComCallableWrapper
    0.23
    æĪijçļĦå¿ĥ
    0.21
    inals
    0.21
    Activations Density 0.171%

    No Known Activations